IRIS RECOGNITION: HOW IT WORKS

Iris recognition continues to be acknowledged as the most accurate biometric identification system available in the world today.

This section explains the use of biometrics and the unique advantages that our IrisCode™ Technology can provide.

	Biometrics is a technology by which unique physical characteristics - the contours of a face, the resonance of a voice, the texture of a fingerprint - are translated into digital codes that identify or verify exactly who you are.
	Iris recognition technology identifies humans by the unique physiological patterns in the iris of the eye to a degree of accuracy surpassing even DNA matching.
	Non-invasive, non-contact and extremely fast, a high-resolution camera captures the image of an iris, translating it into an encrypted digital code. This technology is NOT retina scan technology and no laser is projected into the eye.
	The technology is widely acknowledged within the biometrics industry to be the most accurate, stable, and scalable human authentication system in existence.

Biometric Measurements

During the verification or identification process errors can occur. There are two critical measurement factors which indicate the level of accuracy, or reliability, of any given biometric. They are False Reject Rate (FRR) and False Accept Rate (FAR).

False Reject Rate (FRR)

When a biometric measurement from a live subject is compared to that subject's enrolled template and the system fails to match the two, a "false reject" event occurs. The theoretical probability of this happening, or the actual frequency with which it occurs (if there is sufficient historical data available) is known as the False Reject Rate (FRR). Although FRR's will vary widely amongst different biometric systems and technologies, with any single given biometric system the FRR will be approximately the same whether the process is used for verification or for identification. This is because there is only one authentic template on file against which the live subject can make a match.

The FRR will vary widely depending on the situation under which the biometric is used. Factors such as user co-operation, operating conditions, etc can all effect the FRR.

False Accept Rate (FAR)

There is always a possibility that the measurement from a live subject will be sufficiently similar to a template from another, different, person that a match will be (erroneously) declared. This second type of error is called a "false accept" event and the associated probability is called the false accept rate or FAR. The FAR achieved by a particular biometric directly reflects the fundamental power and specificity of the technology. To achieve a low FAR the biological entity measured must be absolutely unique to the individual, and the algorithm used to measure the entity must capture this uniqueness very effectively.

A comparison between various technologies has been conducted by the UK Government (National Physics Laboratory), an extract of the results being captured in the following table. The table highlights the non existent FAR as well as the inability to sensitise or desensitise the technology across a FRR or FAR range.

The other biometric methods charted above offer scalability between security and ease of access with a trade-off between the FRR and FAR. What this means is that the more secure you desire your security, the more false rejects you will encounter. On the other hand, if you wish to reduce false rejects, you immediately create a much higher false acceptance rate leading to unwanted persons being identified erroneously. As is shown above, IrisCode™ technology offers no scalability and is fixed to the y-axis. The FRR is much lower than that of alternative biometrics and the FAR is fixed at 0.

IrisCode™ Technology

The iris of each eye of each person is absolutely unique. In the entire human population, no two irises are alike in their mathematical detail. This even applies to identical twins.

This iris of each eye is protected from the external environment. It is clearly visible from a distance, making it ideal for a biometric solution. Image acquisition for enrolment and recognition is easily accomplished and most importantly is non-intrusive.

No other biometric technology can rival the combined attributes of mathematical certainty, speed and non-invasive operation offered by iris recognition.

The IrisCode™ creation process starts with video-based image acquisition. This is a purely passive process achieved using CCD Video Cameras. This image is then processed and encoded into an IrisCode™ record, which is stored in an IrisCode™ database. This stored record is then used for identification in any live transaction when an iris is presented for comparison.

In summary, iris recognition is:

site map | privacy | faq
 about us | feedback